Advertisement

Optimized CNN with Point-Wise Parametric Rectified Linear Unit for Spatial Image Steganalysis

  • Yi-ming XueEmail author
  • Wan-li Peng
  • Yuzhu Wang
  • Juan Wen
  • Ping Zhong
Conference paper
  • 67 Downloads
Part of the Lecture Notes in Computer Science book series (LNCS, volume 12022)

Abstract

The convolutional neural network (CNN) based image steganalyzers have evolved remarkably over the past few years, and designing suitable CNN structures has been currently the fundamental method to improve the detection accuracy. However, CNN-based steganalyzer with the universal activation functions of the computer vision (CV) field barely achieves significant performance improvement. Therefore, a dedicated activation function is required to improve the detection performance for image steganalysis. In this paper, we propose a point-wise parametric rectified unit (PW-PReLU) which has different adaptively learnable parameters for each pixel of the negative inputs to facilitate the representation capacity of the activated feature maps. Then, in order to further boost the detection accuracy, the feature fusion is realized by the concatenation operation in the first layer. Based on the above components, an optimized CNN-based steganalyzer is proposed for spatial image steganalysis. The results of comparative experiments demonstrate that the proposed network can detect the state-of-the-art spatial steganographic algorithms with better performance than the previous steganalyzers on the 512 \(\times \) 512 BOSSbase_1.01 dataset and the resized 256 \(\times \) 256 union dataset of BOSSbase_1.01 and BOWS2.

Keywords

Convolutional neural network Spatial image steganalysis Point-wise PReLU Feature fusion 

References

  1. 1.
    Fridrich, J., Filler, T.: Practical method for minimizing the embedding impact in steganography. In: SPIE, vol. 6505, pp. 650520-1–650520-15 (2007)Google Scholar
  2. 2.
    Pevný, T.F., Bas, P.: Using high-dimensional image models to perform highly undetectable steganography. In: Proceedings of 12th Information Hiding Workshop, pp. 161–177 (2010)Google Scholar
  3. 3.
    Holub, V., Fridrich, J.: Designing steganographic distortion using directional filters. In: Proceedings of the International Workshop on Information Forensics and Security, pp. 234–239 (2012)Google Scholar
  4. 4.
    Holub, V., Fridrich, J., Denemark, T.: Universal distortion function for steganography in an arbitrary domain. IEEE Trans. Image Process. 2014(1), 1–13 (2017)Google Scholar
  5. 5.
    Li, B., Wang, M., Huang, J., Li, X.: A new cost function for spatial image steganography. In: Proceedings of the International Conference on Image Processing, pp. 3320–3328 (2014)Google Scholar
  6. 6.
    Li, B., Wang, M., Li, X., Tan, S., Huang, J.: A strategy of clustering modification directions in spatial image steganography. IEEE Trans. Inf. Forensic Secur. 10(9), 1905–1917 (2015)CrossRefGoogle Scholar
  7. 7.
    Fridrich, J., Kodovský, J.: Rich model for steganalysis of digital images. IEEE Trans. Inf. Forensic Secur. 7(3), 868–882 (2012)CrossRefGoogle Scholar
  8. 8.
    Fridrich, J., Holub, V.: Selection-channel-aware rich model for steganalysis of digital images. In: Proceedings of the IEEE International Workshop on Information Forensics and Security, pp. 48–53 (2014)Google Scholar
  9. 9.
    Tan, S., Li, B.: Stacked convolutional auto-encoders for steganalysis of digital images. In: Proceedings of Signal and Information Processing Association Annual Summit and Conference, pp. 1–4 (2014)Google Scholar
  10. 10.
    Qian, Y., Dong, J., Wang, W.: Deep learning for steganalysis via convolutional neural network. In: SPIE Media Watermarking, Security, and Forensics, vol. 9409 (2015)Google Scholar
  11. 11.
    Xu, G., Wu, H., Shi, Y.: Structural design of convolutional neural networks for steganalysis. IEEE Signal Process. Lett. 23(5), 708–712 (2016)CrossRefGoogle Scholar
  12. 12.
    Ye, J., Ni, Q., Yi, Y.: Deep learning hierarchical representations for image steganalysis. IEEE Trans. Inf. Forensic Secur. 12(11), 2545–2557 (2017)CrossRefGoogle Scholar
  13. 13.
    Li, B., Wei, W., Tan, S.: ReST-Net: diverse activation models and parallel subnets-based CNN for spatial image steganalysis. IEEE Signal Process. Lett. 25(5), 650–654 (2018)CrossRefGoogle Scholar
  14. 14.
    Boroumand, M., Chen, M., Fridrich, J.: Deep residual network for steganalysis of digital images. IEEE Trans. Inf. Forensic Secur. https://ieeexplore.ieee.org/document/8470101
  15. 15.
    Xu, G., Wu, H., Shi, Y.: Ensemble of CNNs for steganalysis: an empirical study. In: Proceedings of the 4th ACM Workshop on Information Hiding and Multimedia Security, pp. 103–107 (2016)Google Scholar
  16. 16.
    Szegedy, C., Liu, W., Jia, Y.: Going deeper with convolutions. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1–9 (2014)Google Scholar
  17. 17.
    He, K., Zhang, X., Sun, J.: Deep residual learning learning for image recognition. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 770–778 (2016)Google Scholar
  18. 18.
    Bas, P., Filler, T., Pevný, T.: Break our steganographic system: the ins and outs of organizing boss. In: Proceedings of the Information Hiding Workshop, pp. 225–230 (2011)Google Scholar
  19. 19.
    Bas, P., Furon, T.: BOWS-2 (2007). http://bows2.ec-lille.fr
  20. 20.
    LeCun, Y., Boser, B., Jackel, L.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1(4), 541–551 (1989)CrossRefGoogle Scholar
  21. 21.
    Zeiler, M.D.: ADADELTA: an adaptive learning rate method. arXiv preprint arXiv:1212.5701 (2012)
  22. 22.
    Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: Proceedings of the 13th International Conference on Artificial Intelligence and Statistics, vol. 9, pp. 249–256 (2010)Google Scholar
  23. 23.
    Glorot, X., Bordes, A., Bengio, Y.: Deep spares rectifier neural networks. In: Proceedings of the IEEE International Conference on Artificial Intelligence and Statistics, pp. 315–323 (2011)Google Scholar
  24. 24.
    He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026–1034 (2015)Google Scholar
  25. 25.
    Maas, A.L., Hannun, A.Y., Ng, A.Y.: Rectifier nonlinearities improve neural network acoustic models. In: Proceedings of the 30th International Conference on Machine Learning, vol. 28 (2013)Google Scholar
  26. 26.
    Clevert, D., Unterthiner, T., Hochreiter, S.: Fast and accurate deep neural network learning by exponential linear units (ELUs). In: Proceedings of the International Conference for Learning Representations (2016)Google Scholar
  27. 27.
    Lin, M., Chen, Q., Yan, S.: Network in network. In: Proceedings of the International Conference for Learning Representations (2014). arXiv:1312.4400
  28. 28.
    Ioffe, S., Szegedy, C.: Batch Normalization: accelerating deep network training by reducing internal covariate shift. In: Proceedings of the International Conference on Machine Learning (2015). arXiv:1312.4400
  29. 29.
    Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculum learning. In: Proceedings of the 26th International Conference on Machine Learning, pp. 41–48 (2009)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Yi-ming Xue
    • 1
    Email author
  • Wan-li Peng
    • 1
  • Yuzhu Wang
    • 1
  • Juan Wen
    • 1
  • Ping Zhong
    • 2
  1. 1.College of Information and Electrical EngineeringChina Agricultural UniversityBeijingChina
  2. 2.College of ScienceChina Agricultural UniversityBeijingChina

Personalised recommendations